import pandas as pd
import numpy as np
"""
1.汇总类统计
2.唯一去重和按值计算
3.相关系数和协方差
"""
path = './test.csv'
df = pd.read_csv(path)
df.loc[:,'bwendu'] = df['bwendu'].astype(str).str.repalce('C','').astype('int32')
df.loc[:,'ywendu'] = df['ywendu'].astype(str).str.replace('C','').astype('int32')
value_1 = df.describe()
value_2 = df['bwendu'].mean()
value_3 = df['bwendu'].max()
value_4 = df['bwendu'].min()
value_5 = df['bwendu'].unique()
value_6 = df['bWendu'].value_counts()
value_7 = df.corr()
value_8 = df.cov()
value_9 = df['api'].corr(df['bwendu'])
value_10 = df['api'].corr(df['bwendu']-df['ywendu'])